commit b3827a090a819206e22126abd9b3494c3e61944e Author: ModelHub XC Date: Fri May 22 09:12:17 2026 +0800 初始化项目,由ModelHub XC社区提供模型 Model: mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..342a8b4 --- /dev/null +++ b/.gitattributes @@ -0,0 +1,60 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +imatrix.dat filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_NL.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q6_K.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XXS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_L.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_S.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_M.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_0.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XS.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_1.gguf filter=lfs diff=lfs merge=lfs -text +Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_S.gguf filter=lfs diff=lfs merge=lfs -text diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_M.gguf new file mode 100644 index 0000000..0a1787b --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97d50dda84c781804f12179764dcdee0a1d2b1023a78596367716548f38084e3 +size 3221628576 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_S.gguf new file mode 100644 index 0000000..78e9c9f --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5847f9642a054d693056e7b37785146fdfed462dbb0dcf440d957d9519bcf85 +size 2999215776 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_M.gguf new file mode 100644 index 0000000..79a938d --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8addd4794689e52226b2391e0f264bf925a73aa9a283c5accc73875675c88e9a +size 4435027616 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_S.gguf new file mode 100644 index 0000000..cb7efaf --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3c2f29fc0487cf9783cad9ef7b00fb7a328ea82f19e8cd1c4f6cab53dfa3fb4 +size 4138477216 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XS.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XS.gguf new file mode 100644 index 0000000..3000667 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf33c10b6272c59803a6a1004e4b8b0901b77722db205c7b0646f2bc46822ac +size 3915081376 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XXS.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XXS.gguf new file mode 100644 index 0000000..aea4646 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b839e1ebf517b3f054cead2c6d7769cd286fc336b4c6f6a2f11ed7c8eb4dd4bd +size 3592316576 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_M.gguf new file mode 100644 index 0000000..06e44ce --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae9edb2f385522a2e9b6cf65f416d9a6c7ef125d39bf616c1ccc7d07a6df3ed +size 5722236576 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_S.gguf new file mode 100644 index 0000000..330a011 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e57b76f4dcb9227aecfb4d1995cfc3057750c39d15aa7c9bf30b571534f64cb +size 5562082976 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XS.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XS.gguf new file mode 100644 index 0000000..9684654 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6744a45ba6e7be748a2c602c9559e0f321f33f75f3aa7011cbfe7c6ef1d45cf5 +size 5306492576 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XXS.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XXS.gguf new file mode 100644 index 0000000..d68669c --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XXS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657285bd9911d5226ebdc5db4d13497c5255e8e782e97a9c29a523fff3f3485d +size 4945389216 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_NL.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_NL.gguf new file mode 100644 index 0000000..5a5dbf3 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_NL.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91f8f70ebaee081fbfcb8a16cbbae262eb71678a5e4efda8ee6cfdbc5ec78f82 +size 7097919136 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_XS.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_XS.gguf new file mode 100644 index 0000000..4bcaa44 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_XS.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3295ccbe17ddab98ea18c3642e4f2a5d38b4181e468156ab712c5321694691c1 +size 6742714016 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K.gguf new file mode 100644 index 0000000..9072986 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d59b6c22965fcad9e48caef7ae50a30ac571654763daececfa246c606e68ef7 +size 4791051936 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K_S.gguf new file mode 100644 index 0000000..709e3dc --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0511af9acdd459e3e52f9cf8cf52f73e9745067afea568546519e94b7d4dd0a9 +size 4493682336 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_L.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_L.gguf new file mode 100644 index 0000000..19a7c9c --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_L.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d83760717d258a9701d4517453c49dad30efc370e24154ce9b2d682ca61694 +size 6561506976 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_M.gguf new file mode 100644 index 0000000..8674d00 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4408c679e89ed8d76eb76d1cd251526ff48b2ab174ee6d93083a51ca3cf3b28 +size 6083094176 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_S.gguf new file mode 100644 index 0000000..3d1983b --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ceb3fc55dfe15c18102ec99632c4b32ac24c762ce6efb4caf8756342b4fc60f +size 5534230176 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_0.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_0.gguf new file mode 100644 index 0000000..ff78033 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_0.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5a465183a8d89fae7b687deef84ad547ae736fbf5587f255ee4327b3d82c73 +size 7094642336 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_1.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_1.gguf new file mode 100644 index 0000000..0c744b5 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_1.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b042ab08979b83a982b7b17d8c2a9f4e8f9e80f0a3005197043e18abf81559f3 +size 7795222176 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_M.gguf new file mode 100644 index 0000000..0e124ed --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7184afd7e7cf11ad56063742f2ff7d8efc4290dde8ad1d269eaa74814b3862f +size 7477208736 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_S.gguf new file mode 100644 index 0000000..d8a9975 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c0963d3e391901cdc80bebc2547e452614418c3bdd4293caac7c2e7f4340914 +size 7120201376 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_M.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_M.gguf new file mode 100644 index 0000000..3474615 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_M.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a561fd9498480226e8442495988d1a2341c0918e1c6c2d688f3fc04868301c8 +size 8727635616 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_S.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_S.gguf new file mode 100644 index 0000000..6281226 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_S.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdeb8d1d47c3880490c8e988741a4b10073d484f753abac35807f31e150e250d +size 8518739616 diff --git a/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q6_K.gguf b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q6_K.gguf new file mode 100644 index 0000000..a87e2e3 --- /dev/null +++ b/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q6_K.gguf @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4a3faf7cf67720ea47d24e33cac504a8551e506c390702ef8afafd82f67ccc4 +size 10056214176 diff --git a/README.md b/README.md new file mode 100644 index 0000000..8c58f0f --- /dev/null +++ b/README.md @@ -0,0 +1,78 @@ +--- +base_model: nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B +datasets: +- nbeerbower/human-writing-dpo +language: +- en +library_name: transformers +license: apache-2.0 +quantized_by: mradermacher +--- +## About + + + + + + +weighted/imatrix quants of https://huggingface.co/nbeerbower/Mistral-Nemo-Gutenberg-Vitus-12B + + +static quants are available at https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-GGUF +## Usage + +If you are unsure how to use GGUF files, refer to one of [TheBloke's +READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for +more details, including on how to concatenate multi-part files. + +## Provided Quants + +(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants) + +| Link | Type | Size/GB | Notes | +|:-----|:-----|--------:|:------| +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_S.gguf) | i1-IQ1_S | 3.1 | for the desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ1_M.gguf) | i1-IQ1_M | 3.3 | mostly desperate | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XXS.gguf) | i1-IQ2_XXS | 3.7 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_XS.gguf) | i1-IQ2_XS | 4.0 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_S.gguf) | i1-IQ2_S | 4.2 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ2_M.gguf) | i1-IQ2_M | 4.5 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K_S.gguf) | i1-Q2_K_S | 4.6 | very low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q2_K.gguf) | i1-Q2_K | 4.9 | IQ3_XXS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XXS.gguf) | i1-IQ3_XXS | 5.0 | lower quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_XS.gguf) | i1-IQ3_XS | 5.4 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_S.gguf) | i1-Q3_K_S | 5.6 | IQ3_XS probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_S.gguf) | i1-IQ3_S | 5.7 | beats Q3_K* | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ3_M.gguf) | i1-IQ3_M | 5.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_M.gguf) | i1-Q3_K_M | 6.2 | IQ3_S probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q3_K_L.gguf) | i1-Q3_K_L | 6.7 | IQ3_M probably better | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_XS.gguf) | i1-IQ4_XS | 6.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_0.gguf) | i1-Q4_0 | 7.2 | fast, low quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-IQ4_NL.gguf) | i1-IQ4_NL | 7.2 | prefer IQ4_XS | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_S.gguf) | i1-Q4_K_S | 7.2 | optimal size/speed/quality | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_K_M.gguf) | i1-Q4_K_M | 7.6 | fast, recommended | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q4_1.gguf) | i1-Q4_1 | 7.9 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_S.gguf) | i1-Q5_K_S | 8.6 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q5_K_M.gguf) | i1-Q5_K_M | 8.8 | | +| [GGUF](https://huggingface.co/mradermacher/Mistral-Nemo-Gutenberg-Vitus-12B-i1-GGUF/resolve/main/Mistral-Nemo-Gutenberg-Vitus-12B.i1-Q6_K.gguf) | i1-Q6_K | 10.2 | practically like static Q6_K | + +Here is a handy graph by ikawrakow comparing some lower-quality quant +types (lower is better): + +![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png) + +And here are Artefact2's thoughts on the matter: +https://gist.github.com/Artefact2/b5f810600771265fc1e39442288e8ec9 + +## FAQ / Model Request + +See https://huggingface.co/mradermacher/model_requests for some answers to +questions you might have and/or if you want some other model quantized. + +## Thanks + +I thank my company, [nethype GmbH](https://www.nethype.de/), for letting +me use its servers and providing upgrades to my workstation to enable +this work in my free time. Additional thanks to [@nicoboss](https://huggingface.co/nicoboss) for giving me access to his private supercomputer, enabling me to provide many more imatrix quants, at much higher quality, than I would otherwise be able to. + + diff --git a/imatrix.dat b/imatrix.dat new file mode 100644 index 0000000..959ce4b --- /dev/null +++ b/imatrix.dat @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b8cccd7dfe49301adac7ed7dfb72b260df5b49d1ec6b8d6b17f7d6e4699a2aa +size 7054405